Face Recognition Experiments Research Articles

An Image Retrieval Method Based on Machine Learning and SVM

Image recognition has been a research hotspot in the field of machine learning; this paper puts forward a kind of cascade algorithm based on SVM and AdaBoost. The algorithm to select the sample pretreatment, fixed size of window image segmentation into different areas, then using Haar - like rectangular figure characteristics of integral method for feature extraction, finally using AdaBoost cascade classifier to classify the SVM training. Through the face recognition experiments show AdaBoost cascade of SVM algorithm improve the classification accuracy, error rate get reduced obviously.

A Sparse Representation-Based Face Recognition Using Mixed Group Sparsity

Empirical evidence shows that introducing additional structured priors can reduce complexity of coding data, and achieve better performance. To improve the performance of sparse representation-based classification (SRC), the article based on the potential correlations between the elements of dictionary gets a mixed group sparsity which is composed of dynamic group sparsity and fixed-length group sparsity. To solve the structured sparsity efficiently, structured greedy algorithm (structOMP) is redesigned to fit the new structure. The modification includes search space and its neighbor. Finally, three sparse models are compared by experiments of face recognition, and the results show that the mixed group sparsity can improve the face recognition rate of other sparse models by 10% or more in dealing with corrupted data.

Collaborative representation with reduced residual for face recognition

Collaboration representation-based classification (CRC) was proposed as an alternative approach to the sparse representation method with similar efficiency. The CRC is essentially a competition scheme for the training samples to compete with each other in representing the test sample, and the training class with the minimum representation residual from the test sample wins the competition in the classification. However, the representation error is usually calculated based on the Euclidean distance between a test sample and the weighted sum of all the same-class samples. This paper exploits alternative methods of calculating the representation error in the CRC methods to reduce the representation residual in a more optimal way, so that the sample classes compete with each other in a closer range to represent the test sample. A large number of face recognition experiments on three face image databases show that the CRC methods with optimized presentation residual achieve better performance than the original CRC, and the maximum improvement in classification accuracy is up to 12 %.

Adaptive Discriminant Linear Local Tangent Space Alignment Algorithm on Face Recognition

This paper proposes an adaptive discriminant linear local tangent space alignment algorithm DALLTSA. On the basis of LLTSA algorithm adding adaptive and discriminant gets DALLTSA.DALLTSA not only combines characteristics in DLLTSA that maintain the local geometry and meets the maximum between-class scatter matrix, but also dynamically selects K-neighbor better to reflect the degree of polymerization between samples. Finally, the face recognition experiments based on Gabor [1] filter and DALLTSA shows that this algorithm improves the recognition rate and robustness.

Noise-free representation based classification and face recognition experiments

The representation based classification has achieved promising performance in high-dimensional pattern classification problems. As we know, in real-world applications the samples are usually corrupted by noise. However, representation based classification can take only noise in the test sample into account and is not able to deal with noise in the training sample, which causes side-effect on the classification result. In order to make the representation based classification more suitable for real-world applications such as face recognition, we propose a new representation based classification method in this paper. This method can effectively and simultaneously reduce noise in the test and training samples. Moreover, the proposed method can reduce noise in both the original and virtual training samples and then exploits them to determine the label of the test sample. The virtual training sample is generated from the original face image and shows possible variation of the face in scale, facial pose and expression. The experimental results show that the proposed method performs very well in face recognition.

Comparison of Different Neural Network Architectures for Classification of Feature Transformed Data for Face Recognition

In this paper neural network classifier is applied on transformed shape features for face recognition. Classification by neural networks to a large extent depends on the neural network architecture. We have investigated three different neural network architectures for classification namely-Feed Forward Neural Network, Cascade Feed Forward Neural Network and Radial Basis Function Neural Network and tested their performance for three sets of feature extracted data. For feature extraction we convert the 2-D gray level face images into their respective depth maps or physical shape which are subsequently transformed by three different methods to get three separate data sets,namely-Coiflet Packet , Radon Transform and Fourier Mellin Transform to compute energy for feature extraction. After feature extraction each of the training classes are optimally separated using linear discriminant analysis. The neural network classifiers have been tested on each of the three sets of feature extracted data and a comparative analysis has been done on the results obtained. The proposed algorithms have been tested on the ORL database, widely used for face recognition experiments. General Terms Pattern Recognition, Computer Vision, Artificial Intellegence,Image Processing

The influence of luminance, observation duration and procedure on the recognition of pedestrians’ faces

Past studies carried out to determine whether the spectral power distribution of a light source affects facial recognition have led to mixed results. One reason for this could be that different studies presented different levels of task difficulty, this being a function of target size, observation duration and type of procedure. This paper presents two facial recognition experiments carried out using matching and identification procedures to explore task difficulty as defined by observation duration and target luminance. It was confirmed that identification is more difficult than matching. A relationship between task difficulty (luminance and duration) and recognition probability was found and this allows the luminance to be determined for a given probability.

Improved combination of RPCA and MEL for sparse representation-based face recognition

Face recognition (FR) is an important and challenging task in pattern recognition and has many important practical applications. This paper presents an improved technique for Face Recognition, which consists of two phases where in each phase; a technique is employed effectively that is used extensively in computer vision and pattern recognition. Initially, the Robust Principal Component Analysis (RPCA) is used specifically in the first phase, which is employed to reduce dimensionality and to extract abstract features of faces. The framework of the second phase is sparse representation based classification (SRC) and introduced metaface learning (MFL) of face images. Experiments for face recognition have been performed on ORL and AR face database. It is shown that the proposed method can perform much best than other methods. And with the proposed method, we can obtain a best understanding of data.

Combination of linear regression classification and collaborative representation classification

Classification using the l 2-norm-based representation is usually computationally efficient and is able to obtain high accuracy in the recognition of faces. Among l 2-norm-based representation methods, linear regression classification (LRC) and collaborative representation classification (CRC) have been widely used. LRC and CRC produce residuals in very different ways, but they both use residuals to perform classification. Therefore, by combining the residuals of these two methods, better performance for face recognition can be achieved. In this paper, a simple weighted sum based fusion scheme is proposed to integrate LRC and CRC for more accurate recognition of faces. The rationale of the proposed method is analyzed. Face recognition experiments illustrate that the proposed method outperforms LRC and CRC.

Modified minimum squared error algorithm for robust classification and face recognition experiments

In this paper, we improve the minimum squared error (MSE) algorithm for classification by modifying its classification rule. Differing from the conventional MSE algorithm which first obtains the mapping that can best transform the training sample into its class label and then exploits the obtained mapping to predict the class label of the test sample, the modified minimum squared error classification (MMSEC) algorithm simultaneously predicts the class labels of the test sample and the training samples nearest to it and combines the predicted results to ultimately classify the test sample. Besides this paper, for the first time, proposes the idea to take advantage of the predicted class labels of the training samples for classification of the test sample, it devises a weighted fusion scheme to fuse the predicted class labels of the training sample and test sample. The paper also interprets the rationale of MMSEC. As MMSEC generalizes better than conventional MSE, it can lead to more robust classification decisions. The face recognition experiments show that MMSEC does obtain very promising performance.

Image Recognition Based on Separable Lattice Trajectory 2-D HMMs

In this paper, a novel statistical model for image recognition based on separable lattice 2-D HMMs (SL2D-HMMs) is proposed. Although SL2D-HMMs can model invariance to size and location deformation, its modeling accuracy is still insufficient because of the following two assumptions: i) the statistics of each state are constant and ii) the state output probabilities are conditionally independent. In this paper, SL2D-HMMs are reformulated as a trajectory model that can capture dependencies between adjacent observations. The effectiveness of the proposed model was demonstrated in face recognition and image alignment experiments.

Reconocimiento de rostros y gestos faciales mediante un análisis de relevancia con imágenes 3D

El reconocimiento facial tridimensional busca subsanar las falencias que presentan los métodos basados en imágenes bidimensionales. Este tipo de reconocimiento tiene la ventaja de que las representaciones no son afectadas por cambios en la iluminación, dado que viene dada como una nube de puntos o una malla 3D donde la geometría juega un papel crucial. En este trabajo se presenta un sistema de reconocimiento de rostros, que utiliza un conjunto de descriptores de forma 3D, seleccionados a partir de un análisis de relevancia mediante coeficientes de Fisher en diferentes regiones del rostro que hacen parte de un modelo antropométrico del rostro. Se realizó un conjunto de experimentos para reconocer individuos e identificar sus expresiones y género a partir del análisis de relevancia planteado. Los resultados obtenidos muestran que la elección de características utilizando un análisis de relevancia incrementa el rendimiento del sistema de reconocimiento.

Line‐up Misidentifications: When Being ‘Prototypically Black’ is Perceived as Criminal

SummaryEyewitness misidentifications are the leading factor contributing to wrongful convictions. Black men, more than any other racial group, are disproportionately affected by this, thus elevating the importance of identifying factors that contribute to the false recollection of unseen faces. In the current studies, we tested whether misplaced familiarity and subsequent misidentification of Black faces was underpinned by the degree to which target faces were considered ‘prototypical’ (i.e., representative) of the Black race category. First, results revealed that Black faces with stereotypical facial features were accurately categorized as ‘Black’ quicker than faces with nonstereotypical features (Experiment 1). Moreover, identification errors were higher for both face recognition (Experiment 2) and line‐up identification (Experiment3) for stereotypical‐featured than nonstereotypical‐featured faces. Overall, results suggest that stereotypical Black faces are representative of the category ‘Black’ and facilitated feelings of familiarity and the endorsement of memory errors that may underpin eyewitness misidentifications. Copyright © 2013 John Wiley & Sons, Ltd.

The comparative analysis l2-minimisation based description methods

In this paper, we compare some human face recognition methods which are based l2-minimisation description methods. These face recognition methods include the two-phase test sample sparse representation (TPTSSR) method, an improvement to the nearest neighbor classifier and face recognition experiments (INNC), a simple and fast representation-based face recognition method (SFRFR), feature space-based human face image representation and recognition (FSB), collaborative representation classification with regularized least square (CRC_RLS) and relaxed collaborative representation for pattern classification (RCR). We compare all of these methods in the same condition, such as the same database, same test set and same training set. The experimental results show the performance of these six methods.

A sparse representation method based on kernel and virtual samples for face recognition

To improve the classification accuracy of face recognition, a sparse representation method based on kernel and virtual samples is proposed in this paper. The proposed method has the following basic idea: first, it extends the training samples by copying the left side of the original training samples to the right side to form virtual training samples. Then the virtual training samples and the original training samples make up a new training set and we use a kernel-induced distance to determine M nearest neighbors of the test sample from the new training set. Second, it expresses the test sample as a linear combination of the selected M nearest training samples and finally exploits the determined linear combination to perform classification of the test sample. A large number of face recognition experiments on different face databases illustrate that the error ratios obtained by our method are always lower more or less than face recognition methods including the method mentioned in Xu and Zhu [21], the method proposed in Xu and Zhu [39], sparse representation method based on virtual samples (SRMVS), collaborative representation based classification with regularized least square (CRC_RLS), two-phase test sample sparse representation (TPTSSR), and the feature space-based representation method.

Pattern recognition and increasing of the computational efficiency of a parallel realization of the probabilistic neural network with homogeneity testing

The research subject is the computational complexity of the probabilistic neural network (PNN) in the pattern recognition problem for large model databases. We examined the following methods of increasing the efficiency of a neural-network classifier: a parallel multithread realization, reducing the PNN to a criterion with testing of homogeneity of feature histograms of input and reference images, approximate nearest-neighbor analyses (Best-Bin First, directed enumeration methods). The approach was tested in facial-recognition experiments with FERET dataset.

Face Recognition Using Sparse Representation-Based Classification on K-Nearest Subspace

The sparse representation-based classification (SRC) has been proven to be a robust face recognition method. However, its computational complexity is very high due to solving a complex -minimization problem. To improve the calculation efficiency, we propose a novel face recognition method, called sparse representation-based classification on k-nearest subspace (SRC-KNS). Our method first exploits the distance between the test image and the subspace of each individual class to determine the nearest subspaces and then performs SRC on the selected classes. Actually, SRC-KNS is able to reduce the scale of the sparse representation problem greatly and the computation to determine the nearest subspaces is quite simple. Therefore, SRC-KNS has a much lower computational complexity than the original SRC. In order to well recognize the occluded face images, we propose the modular SRC-KNS. For this modular method, face images are partitioned into a number of blocks first and then we propose an indicator to remove the contaminated blocks and choose the nearest subspaces. Finally, SRC is used to classify the occluded test sample in the new feature space. Compared to the approach used in the original SRC work, our modular SRC-KNS can greatly reduce the computational load. A number of face recognition experiments show that our methods have five times speed-up at least compared to the original SRC, while achieving comparable or even better recognition rates.

New one-versus-all [formula omitted] solving intra–inter class imbalance with extended manifold regularization and localized relative maximum margin

The optimal separating hyperplane with maximum margin plays a central role in the support vector machine (SVM) classifiers, but is exclusively determined by the support vectors that does not take any structure information into account, especially in the one-versus-all (OVA) SVM for the multi-class classification application where the positive samples and negative ones are usually unbalanced. To address this intra–inter class imbalance problem, a new OVA SVM method is proposed by extending manifold regularization and enhancing the relative maximum margin. It aims to minimize the scatter of nearby intra-class point pairs while penalize that of nearby inter-class point pairs not being arbitrarily large through the constraints of marginal separation and manifold regularization. This objective is transformed into a constrained optimization problem that overcomes both the classical SVM's weakness of ignoring the data underlying structure, and the Laplacian SVM's weakness of abandoning class label information and class separation of manifolds. It also takes the positive and negative samples into different consideration according to their unbalanced distribution. Additionally, risk bounds are derived for the proposed formulation based on the theory of Rademacher complexity and the improvement on the bounds of standard SVM is proven. The comparative experiments for multi-class classification, face recognition, and natural image segmentation on several synthetic and benchmark data sets validate the effectiveness of the proposed method and indicate the consideration of both preserving intrinsic within-class manifold structure and bounding the local relative margin between class is helpful to improve the OVA SVM classification performance.

Research on Importance of Texture Information in Face Recognition

This paper presents importance of skin texture information in face recognition. To this end, we perform the illumination normalization on face image in order to extract texture information unaffected by illumination variation. And then apply mask image on each illumination normalized face image to obtain the corresponding texture data, which hardly contain the shape information. Face recognition experiments are carried out by using texture data. Experimental results on Yale face database B and CMU PIE database show that the texture information has considerable ability to distinguish subjects in face recognition.

Face Recognition and Verification Using Photometric Stereo: The Photoface Database and a Comprehensive Evaluation

This paper presents a new database suitable for both 2-D and 3-D face recognition based on photometric stereo (PS): the Photoface database. The database was collected using a custom-made four-source PS device designed to enable data capture with minimal interaction necessary from the subjects. The device, which automatically detects the presence of a subject using ultrasound, was placed at the entrance to a busy workplace and captured 1839 sessions of face images with natural pose and expression. This meant that the acquired data is more realistic for everyday use than existing databases and is, therefore, an invaluable test bed for state-of-the-art recognition algorithms. The paper also presents experiments of various face recognition and verification algorithms using the albedo, surface normals, and recovered depth maps. Finally, we have conducted experiments in order to demonstrate how different methods in the pipeline of PS (i.e., normal field computation and depth map reconstruction) affect recognition and verification performance. These experiments help to 1) demonstrate the usefulness of PS, and our device in particular, for minimal-interaction face recognition, and 2) highlight the optimal reconstruction and recognition algorithms for use with natural-expression PS data. The database can be downloaded from http://www.uwe.ac.uk/research/Photoface.